Merge pull request #3292 from lonvia/faster-country-search

[nominatim.git] / nominatim / api / logging.py

diff --git a/nominatim/api/logging.py b/nominatim/api/logging.py
index 05598660254bd0a42fe04f66c446174e5ce4a515..e16e0bd2d3bdbcab64b7f8c074ddbbe72cc4843e 100644 (file)
--- a/nominatim/api/logging.py
+++ b/nominatim/api/logging.py
@@ -7,10 +7,12 @@
 """
 Functions for specialised logging with HTML output.
 """
 """
 Functions for specialised logging with HTML output.
 """

-from typing import Any, cast
+from typing import Any, Iterator, Optional, List, Tuple, cast, Union, Mapping, Sequence

 from contextvars import ContextVar
 from contextvars import ContextVar

+import datetime as dt

 import textwrap
 import io
 import textwrap
 import io

+import re

 
 import sqlalchemy as sa
 from sqlalchemy.ext.asyncio import AsyncConnection
 
 import sqlalchemy as sa
 from sqlalchemy.ext.asyncio import AsyncConnection


@@ -24,6 +26,13 @@ except ModuleNotFoundError:
     CODE_HIGHLIGHT = False
 
 
     CODE_HIGHLIGHT = False
 
 

+def _debug_name(res: Any) -> str:
+    if res.names:
+        return cast(str, res.names.get('name', next(iter(res.names.values()))))
+
+    return f"Hnr {res.housenumber}" if res.housenumber is not None else '[NONE]'
+
+

 class BaseLogger:
     """ Interface for logging function.
 
 class BaseLogger:
     """ Interface for logging function.
 


@@ -56,23 +65,67 @@ class BaseLogger:
         """
 
 
         """
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
-        """ Print the SQL for the given statement.
+    def table_dump(self, heading: str, rows: Iterator[Optional[List[Any]]]) -> None:
+        """ Print the table generated by the generator function.

         """
 
         """
 

-    def format_sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> str:
-        """ Return the comiled version of the statement.
+
+    def result_dump(self, heading: str, results: Iterator[Tuple[Any, Any]]) -> None:
+        """ Print a list of search results generated by the generator function.

         """
         """

-        try:
-            return str(cast('sa.ClauseElement', statement)
-                         .compile(conn.sync_engine, compile_kwargs={"literal_binds": True}))
-        except sa.exc.CompileError:
-            pass
-        except NotImplementedError:
-            pass

 
 

-        return str(cast('sa.ClauseElement', statement).compile(conn.sync_engine))

 
 

+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:
+        """ Print the SQL for the given statement.
+        """
+
+    def format_sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+                   extra_params: Union[Mapping[str, Any],
+                                 Sequence[Mapping[str, Any]], None]) -> str:
+        """ Return the comiled version of the statement.
+        """
+        compiled = cast('sa.ClauseElement', statement).compile(conn.sync_engine)
+
+        params = dict(compiled.params)
+        if isinstance(extra_params, Mapping):
+            for k, v in extra_params.items():
+                if hasattr(v, 'to_wkt'):
+                    params[k] = v.to_wkt()
+                elif isinstance(v, (int, float)):
+                    params[k] = v
+                else:
+                    params[k] = str(v)
+        elif isinstance(extra_params, Sequence) and extra_params:
+            for k in extra_params[0]:
+                params[k] = f':{k}'
+
+        sqlstr = str(compiled)
+
+        if conn.dialect.name == 'postgresql':
+            if sa.__version__.startswith('1'):
+                try:
+                    sqlstr = re.sub(r'__\[POSTCOMPILE_[^]]*\]', '%s', sqlstr)
+                    return sqlstr % tuple((repr(params.get(name, None))
+                                          for name in compiled.positiontup)) # type: ignore
+                except TypeError:
+                    return sqlstr
+
+            # Fixes an odd issue with Python 3.7 where percentages are not
+            # quoted correctly.
+            sqlstr = re.sub(r'%(?!\()', '%%', sqlstr)
+            sqlstr = re.sub(r'__\[POSTCOMPILE_([^]]*)\]', r'%(\1)s', sqlstr)
+            return sqlstr % params
+
+        assert conn.dialect.name == 'sqlite'
+
+        # params in positional order
+        pparams = (repr(params.get(name, None)) for name in compiled.positiontup) # type: ignore
+
+        sqlstr = re.sub(r'__\[POSTCOMPILE_([^]]*)\]', '?', sqlstr)
+        sqlstr = re.sub(r"\?", lambda m: next(pparams), sqlstr)
+
+        return sqlstr

 
 class HTMLLogger(BaseLogger):
     """ Logger that formats messages in HTML.
 
 class HTMLLogger(BaseLogger):
     """ Logger that formats messages in HTML.


@@ -81,11 +134,16 @@ class HTMLLogger(BaseLogger):
         self.buffer = io.StringIO()
 
 
         self.buffer = io.StringIO()
 
 

+    def _timestamp(self) -> None:
+        self._write(f'<p class="timestamp">[{dt.datetime.now()}]</p>')
+
+

     def get_buffer(self) -> str:
         return HTML_HEADER + self.buffer.getvalue() + HTML_FOOTER
 
 
     def function(self, func: str, **kwargs: Any) -> None:
     def get_buffer(self) -> str:
         return HTML_HEADER + self.buffer.getvalue() + HTML_FOOTER
 
 
     def function(self, func: str, **kwargs: Any) -> None:

+        self._timestamp()

         self._write(f"<h1>Debug output for {func}()</h1>\n<p>Parameters:<dl>")
         for name, value in kwargs.items():
             self._write(f'<dt>{name}</dt><dd>{self._python_var(value)}</dd>')
         self._write(f"<h1>Debug output for {func}()</h1>\n<p>Parameters:<dl>")
         for name, value in kwargs.items():
             self._write(f'<dt>{name}</dt><dd>{self._python_var(value)}</dd>')


@@ -93,19 +151,77 @@ class HTMLLogger(BaseLogger):
 
 
     def section(self, heading: str) -> None:
 
 
     def section(self, heading: str) -> None:

+        self._timestamp()

         self._write(f"<h2>{heading}</h2>")
 
 
     def comment(self, text: str) -> None:
         self._write(f"<h2>{heading}</h2>")
 
 
     def comment(self, text: str) -> None:

+        self._timestamp()

         self._write(f"<p>{text}</p>")
 
 
     def var_dump(self, heading: str, var: Any) -> None:
         self._write(f"<p>{text}</p>")
 
 
     def var_dump(self, heading: str, var: Any) -> None:

+        self._timestamp()
+        if callable(var):
+            var = var()
+

         self._write(f'<h5>{heading}</h5>{self._python_var(var)}')
 
 
         self._write(f'<h5>{heading}</h5>{self._python_var(var)}')
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
-        sqlstr = self.format_sql(conn, statement)
+    def table_dump(self, heading: str, rows: Iterator[Optional[List[Any]]]) -> None:
+        self._timestamp()
+        head = next(rows)
+        assert head
+        self._write(f'<table><thead><tr><th colspan="{len(head)}">{heading}</th></tr><tr>')
+        for cell in head:
+            self._write(f'<th>{cell}</th>')
+        self._write('</tr></thead><tbody>')
+        for row in rows:
+            if row is not None:
+                self._write('<tr>')
+                for cell in row:
+                    self._write(f'<td>{cell}</td>')
+                self._write('</tr>')
+        self._write('</tbody></table>')
+
+
+    def result_dump(self, heading: str, results: Iterator[Tuple[Any, Any]]) -> None:
+        """ Print a list of search results generated by the generator function.
+        """
+        self._timestamp()
+        def format_osm(osm_object: Optional[Tuple[str, int]]) -> str:
+            if not osm_object:
+                return '-'
+
+            t, i = osm_object
+            if t == 'N':
+                fullt = 'node'
+            elif t == 'W':
+                fullt = 'way'
+            elif t == 'R':
+                fullt = 'relation'
+            else:
+                return f'{t}{i}'
+
+            return f'<a href="https://www.openstreetmap.org/{fullt}/{i}">{t}{i}</a>'
+
+        self._write(f'<h5>{heading}</h5><p><dl>')
+        total = 0
+        for rank, res in results:
+            self._write(f'<dt>[{rank:.3f}]</dt>  <dd>{res.source_table.name}(')
+            self._write(f"{_debug_name(res)}, type=({','.join(res.category)}), ")
+            self._write(f"rank={res.rank_address}, ")
+            self._write(f"osm={format_osm(res.osm_object)}, ")
+            self._write(f'cc={res.country_code}, ')
+            self._write(f'importance={res.importance or float("nan"):.5f})</dd>')
+            total += 1
+        self._write(f'</dl><b>TOTAL:</b> {total}</p>')
+
+
+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:
+        self._timestamp()
+        sqlstr = self.format_sql(conn, statement, params)

         if CODE_HIGHLIGHT:
             sqlstr = highlight(sqlstr, PostgresLexer(),
                                HtmlFormatter(nowrap=True, lineseparator='<br />'))
         if CODE_HIGHLIGHT:
             sqlstr = highlight(sqlstr, PostgresLexer(),
                                HtmlFormatter(nowrap=True, lineseparator='<br />'))


@@ -116,7 +232,7 @@ class HTMLLogger(BaseLogger):
 
     def _python_var(self, var: Any) -> str:
         if CODE_HIGHLIGHT:
 
     def _python_var(self, var: Any) -> str:
         if CODE_HIGHLIGHT:

-            fmt = highlight(repr(var), PythonLexer(), HtmlFormatter(nowrap=True))
+            fmt = highlight(str(var), PythonLexer(), HtmlFormatter(nowrap=True))

             return f'<div class="highlight"><code class="lang-python">{fmt}</code></div>'
 
         return f'<code class="lang-python">{str(var)}</code>'
             return f'<div class="highlight"><code class="lang-python">{fmt}</code></div>'
 
         return f'<code class="lang-python">{str(var)}</code>'


@@ -135,6 +251,10 @@ class TextLogger(BaseLogger):
         self.buffer = io.StringIO()
 
 
         self.buffer = io.StringIO()
 
 

+    def _timestamp(self) -> None:
+        self._write(f'[{dt.datetime.now()}]\n')
+
+

     def get_buffer(self) -> str:
         return self.buffer.getvalue()
 
     def get_buffer(self) -> str:
         return self.buffer.getvalue()
 


@@ -147,6 +267,7 @@ class TextLogger(BaseLogger):
 
 
     def section(self, heading: str) -> None:
 
 
     def section(self, heading: str) -> None:

+        self._timestamp()

         self._write(f"\n# {heading}\n\n")
 
 
         self._write(f"\n# {heading}\n\n")
 
 


@@ -155,11 +276,52 @@ class TextLogger(BaseLogger):
 
 
     def var_dump(self, heading: str, var: Any) -> None:
 
 
     def var_dump(self, heading: str, var: Any) -> None:

+        if callable(var):
+            var = var()
+

         self._write(f'{heading}:\n  {self._python_var(var)}\n\n')
 
 
         self._write(f'{heading}:\n  {self._python_var(var)}\n\n')
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
-        sqlstr = '\n| '.join(textwrap.wrap(self.format_sql(conn, statement), width=78))
+    def table_dump(self, heading: str, rows: Iterator[Optional[List[Any]]]) -> None:
+        self._write(f'{heading}:\n')
+        data = [list(map(self._python_var, row)) if row else None for row in rows]
+        assert data[0] is not None
+        num_cols = len(data[0])
+
+        maxlens = [max(len(d[i]) for d in data if d) for i in range(num_cols)]
+        tablewidth = sum(maxlens) + 3 * num_cols + 1
+        row_format = '| ' +' | '.join(f'{{:<{l}}}' for l in maxlens) + ' |\n'
+        self._write('-'*tablewidth + '\n')
+        self._write(row_format.format(*data[0]))
+        self._write('-'*tablewidth + '\n')
+        for row in data[1:]:
+            if row:
+                self._write(row_format.format(*row))
+            else:
+                self._write('-'*tablewidth + '\n')
+        if data[-1]:
+            self._write('-'*tablewidth + '\n')
+
+
+    def result_dump(self, heading: str, results: Iterator[Tuple[Any, Any]]) -> None:
+        self._timestamp()
+        self._write(f'{heading}:\n')
+        total = 0
+        for rank, res in results:
+            self._write(f'[{rank:.3f}]  {res.source_table.name}(')
+            self._write(f"{_debug_name(res)}, type=({','.join(res.category)}), ")
+            self._write(f"rank={res.rank_address}, ")
+            self._write(f"osm={''.join(map(str, res.osm_object or []))}, ")
+            self._write(f'cc={res.country_code}, ')
+            self._write(f'importance={res.importance or -1:.5f})\n')
+            total += 1
+        self._write(f'TOTAL: {total}\n\n')
+
+
+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:
+        self._timestamp()
+        sqlstr = '\n| '.join(textwrap.wrap(self.format_sql(conn, statement, params), width=78))

         self._write(f"| {sqlstr}\n\n")
 
 
         self._write(f"| {sqlstr}\n\n")
 
 


@@ -242,6 +404,26 @@ HTML_HEADER: str = """<!DOCTYPE html>
         padding: 3pt;
         border: solid lightgrey 0.1pt
     }
         padding: 3pt;
         border: solid lightgrey 0.1pt
     }

+
+    table, th, tbody {
+        border: thin solid;
+        border-collapse: collapse;
+    }
+    td {
+        border-right: thin solid;
+        padding-left: 3pt;
+        padding-right: 3pt;
+    }
+
+    .timestamp {
+        font-size: 0.8em;
+        color: darkblue;
+        width: calc(100% - 5pt);
+        text-align: right;
+        position: absolute;
+        left: 0;
+        margin-top: -5px;
+    }

   </style>
 </head>
 <body>
   </style>
 </head>
 <body>